第34课：Stage划分和Task最佳位置算法源码彻底解密

一：Stage 划分算法解密

    1.spark Application 中可以因为不同的action触发众多的JOB，也就是说一个Application可以产生很多job，每个job是由一个或者多个stage构成的，后面的的stage依赖前面的Stage，也就是说只有只有前面依赖的Stage计算完成，后面的Stage才会运行

   2.Stage 划分的时候会产生宽依赖，什么算子会产生宽依赖？比如reduceByKey、groupByKey、等等。

   3.以RDD的算子collect为列：

 

<span style="font-size:18px;"> /**
   * Return an array that contains all of the elements in this RDD.
   *
   * @note this method should only be used if the resulting array is expected to be small, as
   * all the data is loaded into the driver's memory.
   */
  def collect(): Array[T] = withScope {
    val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray)
    Array.concat(results: _*)
  }</span>

    最终调用：

   def runJob[T, U: ClassTag](

      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      resultHandler: (Int, U) => Unit): Unit = {
    if (stopped.get()) {
      throw new IllegalStateException("SparkContext has been shutdown")
    }
    val callSite = getCallSite
    val cleanedFunc = clean(func)
    logInfo("Starting job: " + callSite.shortForm)
    if (conf.getBoolean("spark.logLineage", false)) {
      logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
    }
    dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
    progressBar.foreach(_.finishAll())
    rdd.doCheckpoint()
  }

   最后由DAGScheduler来进行任务的Stage划分：

   

def runJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      resultHandler: (Int, U) => Unit,
      properties: Properties): Unit = {
    val start = System.nanoTime
    <span style="background-color: rgb(255, 0, 0);">val waiter = submitJob(rdd, func, partitions, callSite, resultHandler, properties)</span>
    Await.ready(waiter.completionFuture, atMost = Duration.Inf)
    waiter.completionFuture.value.get match {
      case scala.util.Success(_) =>
        logInfo("Job %d finished: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
      case scala.util.Failure(exception) =>
        logInfo("Job %d failed: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
        // SPARK-8644: Include user stack trace in exceptions coming from DAGScheduler.
        val callerStackTrace = Thread.currentThread().getStackTrace.tail
        exception.setStackTrace(exception.getStackTrace ++ callerStackTrace)
        throw exception
    }
  }

  我们关注 submitJob 这个方法：

 

def submitJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      resultHandler: (Int, U) => Unit,
      properties: Properties): JobWaiter[U] = {
    // Check to make sure we are not launching a task on a partition that does not exist.
    val maxPartitions = rdd.partitions.length
    partitions.find(p => p >= maxPartitions || p < 0).foreach { p =>
      throw new IllegalArgumentException(
        "Attempting to access a non-existent partition: " + p + ". " +
          "Total number of partitions: " + maxPartitions)
    }

    val jobId = nextJobId.getAndIncrement()
    if (partitions.size == 0) {
      // Return immediately if the job is running 0 tasks
      return new JobWaiter[U](this, jobId, 0, resultHandler)
    }

    assert(partitions.size > 0)
    val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _]
    val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
    eventProcessLoop.post(JobSubmitted(
      jobId, rdd, func2, partitions.toArray, callSite, waiter,
      SerializationUtils.clone(properties)))
    waiter
  }

    

   我们可以看到这里使用了一个消息循环体来post job提交的消息：

  EventLoop 这里有一个 LinkedBlockingDeque 来做消息循环队列

   

private val eventThread = new Thread(name) {
    setDaemon(true)

    override def run(): Unit = {
      try {
        while (!stopped.get) {
          val event = eventQueue.take()
          try {
            onReceive(event)
          } catch {
            case NonFatal(e) => {
              try {
                onError(e)
              } catch {
                case NonFatal(e) => logError("Unexpected error in " + name, e)
              }
            }
          }
        }
      } catch {
        case ie: InterruptedException => // exit even if eventQueue is not empty
        case NonFatal(e) => logError("Unexpected error in " + name, e)
      }
    }

  而DAGScheduler 通过DAGSchedulerEventProcessLoop 的实例来进行任务的调度：

 

private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
    case JobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties) =>
      dagScheduler.handleJobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties)

    case MapStageSubmitted(jobId, dependency, callSite, listener, properties) =>
      dagScheduler.handleMapStageSubmitted(jobId, dependency, callSite, listener, properties)

    case StageCancelled(stageId) =>
      dagScheduler.handleStageCancellation(stageId)

    case JobCancelled(jobId) =>
      dagScheduler.handleJobCancellation(jobId)

    case JobGroupCancelled(groupId) =>
      dagScheduler.handleJobGroupCancelled(groupId)

    case AllJobsCancelled =>
      dagScheduler.doCancelAllJobs()

    case ExecutorAdded(execId, host) =>
      dagScheduler.handleExecutorAdded(execId, host)

    case ExecutorLost(execId) =>
      dagScheduler.handleExecutorLost(execId, fetchFailed = false)

    case BeginEvent(task, taskInfo) =>
      dagScheduler.handleBeginEvent(task, taskInfo)

    case GettingResultEvent(taskInfo) =>
      dagScheduler.handleGetTaskResult(taskInfo)

    case completion: CompletionEvent =>
      dagScheduler.handleTaskCompletion(completion)

    case TaskSetFailed(taskSet, reason, exception) =>
      dagScheduler.handleTaskSetFailed(taskSet, reason, exception)

    case ResubmitFailedStages =>
      dagScheduler.resubmitFailedStages()
  }

   这样DAGScheduler  对外就可以用统一的方式来获取任务的执行的相关的事件（使用队列来解耦）

  最终调用handleJobSubmitted 这个方法：

  

private[scheduler] def handleJobSubmitted(jobId: Int,
      finalRDD: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      callSite: CallSite,
      listener: JobListener,
      properties: Properties) {
    var finalStage: ResultStage = null
    try {
      // New stage creation may throw an exception if, for example, jobs are run on a
      // HadoopRDD whose underlying HDFS files have been deleted.
      finalStage = newResultStage(finalRDD, func, partitions, jobId, callSite)
    } catch {
      case e: Exception =>
        logWarning("Creating new stage failed due to exception - job: " + jobId, e)
        listener.jobFailed(e)
        return
    }

    val job = new ActiveJob(jobId, finalStage, callSite, listener, properties)
    clearCacheLocs()
    logInfo("Got job %s (%s) with %d output partitions".format(
      job.jobId, callSite.shortForm, partitions.length))
    logInfo("Final stage: " + finalStage + " (" + finalStage.name + ")")
    logInfo("Parents of final stage: " + finalStage.parents)
    logInfo("Missing parents: " + getMissingParentStages(finalStage))

    val jobSubmissionTime = clock.getTimeMillis()
    jobIdToActiveJob(jobId) = job
    activeJobs += job
    finalStage.setActiveJob(job)
    val stageIds = jobIdToStageIds(jobId).toArray
    val stageInfos = stageIds.flatMap(id => stageIdToStage.get(id).map(_.latestInfo))
    listenerBus.post(
      SparkListenerJobStart(job.jobId, jobSubmissionTime, stageInfos, properties))
    submitStage(finalStage)

    submitWaitingStages()
  }

    创建newResultStage：

    

private def newResultStage(
      rdd: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      jobId: Int,
      callSite: CallSite): ResultStage = {
    val (parentStages: List[Stage], id: Int) = getParentStagesAndId(rdd, jobId)
    val stage = new ResultStage(id, rdd, func, partitions, parentStages, jobId, callSite)
    stageIdToStage(id) = stage
    updateJobIdStageIdMaps(jobId, stage)
    stage
  }

  我们关注：getParentStagesAndId 方法：

  

private def getParentStagesAndId(rdd: RDD[_], firstJobId: Int): (List[Stage], Int) = {
    val parentStages = getParentStages(rdd, firstJobId)
    val id = nextStageId.getAndIncrement()
    (parentStages, id)
  }

parentStages 是一个scala.List[Stage] 数据结构，也就是Stage的父Stage集合

 private def getParentStages(rdd: RDD[_], firstJobId: Int): List[Stage] = {
    val parents = new HashSet[Stage]
    val visited = new HashSet[RDD[_]]
    // We are manually maintaining a stack here to prevent StackOverflowError
    // caused by recursively visiting
    val waitingForVisit = new Stack[RDD[_]]
    def visit(r: RDD[_]) {
      if (!visited(r)) {
        visited += r
        // Kind of ugly: need to register RDDs with the cache here since
        // we can't do it in its constructor because # of partitions is unknown
        for (dep <- r.dependencies) {
          dep match {
            case shufDep: ShuffleDependency[_, _, _] =>
              parents += getShuffleMapStage(shufDep, firstJobId)
            case _ =>
              waitingForVisit.push(dep.rdd)
          }
        }
      }
    }
    waitingForVisit.push(rdd)
    while (waitingForVisit.nonEmpty) {
      visit(waitingForVisit.pop())
    }
    parents.toList
  }

这里使用广度优先搜索来搜索已经访问过的Stage

数据本地性在DAGScheduler 划分Stage阶段就已经完成了！！！

getShuffleMapStage ： 获取当前Stage 依赖的父Stage

private def getShuffleMapStage(
      shuffleDep: ShuffleDependency[_, _, _],
      firstJobId: Int): ShuffleMapStage = {
    shuffleToMapStage.get(shuffleDep.shuffleId) match {
      case Some(stage) => stage
      case None =>
        // We are going to register ancestor shuffle dependencies
        getAncestorShuffleDependencies(shuffleDep.rdd).foreach { dep =>
          shuffleToMapStage(dep.shuffleId) = newOrUsedShuffleStage(dep, firstJobId)
        }
        // Then register current shuffleDep
        val stage = newOrUsedShuffleStage(shuffleDep, firstJobId)
        shuffleToMapStage(shuffleDep.shuffleId) = stage
        stage
    }
  }

获取Stage的时候，如果没有创建Stage就创建新的Stage，否则直接返回，在从后往前的回溯中会不断的创建新的Stage

我们回到handleJobSubmitted 这个方法中的 submitStage(finalStage)：

private def submitStage(stage: Stage) {
    val jobId = activeJobForStage(stage)
    if (jobId.isDefined) {
      logDebug("submitStage(" + stage + ")")
      if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
        val missing = getMissingParentStages(stage).sortBy(_.id)
        logDebug("missing: " + missing)
        if (missing.isEmpty) {
          logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
          submitMissingTasks(stage, jobId.get)
        } else {
          for (parent <- missing) {
            submitStage(parent)
          }
          waitingStages += stage
        }
      }
    } else {
      abortStage(stage, "No active job for stage " + stage.id, None)
    }
  }

这里递归的提交stage直到该Stage没有依赖的父Stage为止，也就是说父Stage会先进行计算，直到父Stage全部完成子Stage才会开始计算！

val rddHasUncachedPartitions = getCacheLocs(rdd).contains(Nil)

这里会还查看该Stage是否已经计算过，否则不参与计算

二：Task任务本地性

val taskIdToLocations: Map[Int, Seq[TaskLocation]] = try {
      stage match {
        case s: ShuffleMapStage =>
          partitionsToCompute.map { id => (id, getPreferredLocs(stage.rdd, id))}.toMap
        case s: ResultStage =>
          val job = s.activeJob.get
          partitionsToCompute.map { id =>
            val p = s.partitions(id)
            (id, getPreferredLocs(stage.rdd, p))
          }.toMap
      }

此处调用getPreferredLocs 来获取 TaskLocation的位置：

private def getPreferredLocsInternal(
      rdd: RDD[_],
      partition: Int,
      visited: HashSet[(RDD[_], Int)]): Seq[TaskLocation] = {
    // If the partition has already been visited, no need to re-visit.
    // This avoids exponential path exploration.  SPARK-695
    if (!visited.add((rdd, partition))) {
      // Nil has already been returned for previously visited partitions.
      return Nil
    }
    // If the partition is cached, return the cache locations
    val cached = getCacheLocs(rdd)(partition)
    if (cached.nonEmpty) {
      return cached
    }
    // If the RDD has some placement preferences (as is the case for input RDDs), get those
    val rddPrefs = rdd.preferredLocations(rdd.partitions(partition)).toList
    if (rddPrefs.nonEmpty) {
      return rddPrefs.map(TaskLocation(_))
    }

    // If the RDD has narrow dependencies, pick the first partition of the first narrow dependency
    // that has any placement preferences. Ideally we would choose based on transfer sizes,
    // but this will do for now.
    rdd.dependencies.foreach {
      case n: NarrowDependency[_] =>
        for (inPart <- n.getParents(partition)) {
          val locs = getPreferredLocsInternal(n.rdd, inPart, visited)
          if (locs != Nil) {
            return locs
          }
        }

      case _ =>
    }

    Nil
  }

<pre name="code" class="java">TaskLocation 数据结构：保存了当前主机信息和executorId

new ExecutorCacheTaskLocation(host, executorId)

最终从

val rddPrefs = rdd.preferredLocations(rdd.partitions(partition)).toList

RDD中获取数据位置，而RDD中的getPreferredLocations是一个抽象方法，因此用户想要自定义RDD必须重写此方法

override def getPreferredLocations(split: Partition): Seq[String] = {
    val hsplit = split.asInstanceOf[HadoopPartition].inputSplit.value
    val locs: Option[Seq[String]] = HadoopRDD.SPLIT_INFO_REFLECTIONS match {
      case Some(c) =>
        try {
          val lsplit = c.inputSplitWithLocationInfo.cast(hsplit)
          val infos = c.getLocationInfo.invoke(lsplit).asInstanceOf[Array[AnyRef]]
          Some(HadoopRDD.convertSplitLocationInfo(infos))
        } catch {
          case e: Exception =>
            logDebug("Failed to use InputSplitWithLocations.", e)
            None
        }
      case None => None
    }
    locs.getOrElse(hsplit.getLocations.filter(_ != "localhost"))
  }

此方法为HadoopRDD的实现

数据本地性巧妙的借助了RDD中的getPreferredLocations 最大化的提高了效率，因为getPreferredLocations 中表现了每个Partion的数据本地性